Input¶
The Input is a short term JSON data object that is generated each time a message is sent to Cognigy.AI.
The input object contains general information about the message such as the Time the message was received and the Channel from where the message was sent. More specific results from the NLU intent mapping process are also available, such as the Intent that was selected, the Slots that were identified and many other useful pieces of information.
The input object is passed to the Project's Flow to decide on the next action to take. For more information about the lifespan of the input, see the CognigyScript page.
Intent Default Replies override flow logic
If an intent is configured with a default reply, this will override the AI Agent's flow logic and automatically be delivered as the response.
Properties¶
Deprecation of Understood Messages
With Cognigy.AI 4.91, the Understood Messages concept was deprecated. The shutdown date is June 2025. Use the Goals and Tasks concepts to evaluate whether your AI Agent understood a particular phrase.
Refer to the list of all upcoming removals on the Deprecations and Removals page.
The Input object contains the following properties (for text input).
| Key | Description |
|---|---|
| activeQuestion | This property is optional. Information on question execution when a question is active. The following properties are available: nodeId: The question node's ID. type: The type of question lastExecutedAt: Index of last execution. forgetQuestionThreshold: Configured threshold to forget the question. repromptCount: Count of reprompts. escalationCount: Count of escalations. |
| channel | The channel from which the message was received, for example, a Facebook endpoint has the value facebook. For our more generic endpoint types like socket, webhook and rest, this value can be defined. This property will also be available in the OData records to enable channel based analytics filtering. |
| conditionalEntrypointWasExecuted | A boolean variable that displays true if the flow was executed on a conditional node. |
| currentTime | The timestamp of when the message was received by Cognigy.AI. |
| data | The data object that was sent as a payload to the user input. This object can contain a request property that stores the original request from the external channel, for example, If a Facebook endpoint is used, input.data.request will contain the original HTTP request content from Facebook. |
| endpointType | The type of endpoint through which the message was received, for example, Alexa, Facebook (Meta), Dialogflow, etc. This value cannot be changed. |
| entrypoint | This property varies based on Snapshot usage: - The Project ID when no Snapshot is used.- The Snapshot ID when a Snapshot is used. |
| execution | The number of messages received so far in the current session. |
| flowName | The name of the active flow which will process the input data and decide the next action to take. |
| inputId | A unique ID that is generated for each message received by Cognigy.AI. |
| intent | The detected Intent, can be null. |
| intentFlow | The flow containing the detected intent. |
| intentLevel | The matched Intent, per Intent Hierarchy level. |
| intentOutOfState | If a state is active, this property contains the detected intent that has been excluded by the state. |
| intentScore | The detected Intent's score. |
| language | The locale language that was used to process the input message. |
| localeId | The unique ID for the current locale used to process the input message. |
| mode | The type of input received by Cognigy.AI. Can be either TextOnly or TextData. |
| nlu | Contains the detailed NLU processing results. See NLU Properties for detailed information. |
| sessionId | The current session ID. This is either provided by a channel or generated by Cognigy.AI. Most endpoints allow defining an individual session expiration (TTL). |
| slots | Contains the detected slots ranging from automatic to custom lexicon libraries. |
| state | The current state within the session. By default, it will contain the value default. Other states can be defined. See State for more information. |
| text | The text of the message received. |
| traceId | A unique identifier for the specific user input. |
| type | The type of input sentence as determined by the NLU (Statement, Command, Greeting, BGreeting, whQuestion, howQuestion, ynQuestion, pAnswer, nAnswer) question States if a question was received as the input text and what type of question was asked. |
| understood | An input is considered understood if any of the following conditions are met:- An Intent or Slot is identified. - The input is marked as understood through the Nodes: Code, Overwrite Analytics, Search Extract Output, or AI Agent. - The sentence type is pAnswer, nAnswer, or Greeting (if Confirmation Word logic is activated).n input is considered not understood if any of the following conditions are met:- There is an active handover without triggering an AI Copilot Whisper Flow. - The message is explicitly marked as Don't count or Null. |
| URLToken | A unique ID used to identify the specific endpoint. |
| userId | The current user's ID. This is what Cognigy.AI uses to identify each user as a reference to their individual contact profile. See Contact Profiles for more information. |
NLU Properties¶
The detailed NLU results are published to the nlu variable which contains the following properties:
| Key | Description |
|---|---|
| detailedSlots | Contains the detected slots ranging from automatic to custom lexicon libraries. |
| intentId | A unique id assigned to the intent that was selected by the NLU. |
| intentFlow | A unique id assigned to the flow containing the selected intent. |
| intentMapperResults | Provides specific details about the NLU intent mapping results that includes a summary of the intent scoring for each of the trained intents located in the scores child property. |
| tokens | Provides an array containing each word of the input sentence as a string element. |
NLU Properties are available after NLU only
The below properties below are computed by the NLU Connector.
Consequently they are published after the NLU.
They are thus not available inside Cognigy NLU Rules and Conditions.
Properties written by the NLU into the Input:
- intent
- intentScore
- nlu
- type
- intentLevel
- localeId
- understood
- conditionalEntrypointWasExecuted
Accessing the Input Object¶
Flow nodes can dynamically access Input properties via Tokens or CognigyScript i.e. {{input.property}}. The Cognigy Script used to access the input object follows the dot-notation property.child.child.
Example: {{input.text}} would return the text message that was sent to the Flow.
Copy JSON Path from the Input Object
You can copy the exact JSON path you need to reference a certain value in the Input object by right-clicking it and selecting "Copy JSON Path" from the context menu.